© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 46369
    Prev
    Next
    INDEX
    Explanations

    code implementation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Above
    -0.07
    indruck
    -0.07
    Enums
    -0.07
    éĩ
    -0.07
    mpr
    -0.07
    idem
    -0.07
    ä¸ĩæĸ¹
    -0.07
    åĨ¶
    -0.07
    elos
    -0.07
    ино
    -0.07
    POSITIVE LOGITS
    å¦Ĥä¸ĭ
    0.13
    åħ·ä½ĵå¦Ĥä¸ĭ
    0.13
    代çłģå¦Ĥä¸ĭ
    0.12
    åĨĻéģĵ
    0.10
    å¦Ĥä¸ĭåĽ¾
    0.10
     à¸Ķัà¸ĩà¸Ļีà¹ī
    0.10
    计ç®Ĺåħ¬å¼ı
    0.10
     ëĭ¤ìĿĮê³¼
    0.09
     ÅŁÃ¶yle
    0.09
    åħ¬å¼ı
    0.09
    Activations Density 0.731%

    No Known Activations